Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

TL;DR

This paper introduces WAS, a novel framework that decouples the processes of selecting and weighing multiple graph pre-training tasks at the instance level, improving integration and performance across diverse graph datasets.

Contribution

It proposes a decoupled siamese network approach for instance-level task selection and weighing in graph pre-training, addressing the gap in existing methods.

Findings

WAS achieves comparable performance to leading methods on 16 graph datasets.

Decoupling selection and weighing improves integration of multiple pre-training tasks.

The framework is effective across node-level and graph-level tasks.

Abstract

Recent years have witnessed the great success of graph pre-training for graph representation learning. With hundreds of graph pre-training tasks proposed, integrating knowledge acquired from multiple pre-training tasks has become a popular research topic. In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance. While there currently has been a lot of work focused on weighing, comparatively little effort has been devoted to selecting. This paper proposes a novel instance-level framework for integrating multiple graph pre-training tasks, Weigh And Select (WAS), where the two collaborative processes, weighing and selecting, are combined by decoupled siamese networks. Specifically, it first adaptively learns an optimal combination of tasks for each instance from a given task pool, based on which a customized instance-level task weighing strategy is learned. Extensive experiments on 16 graph datasets across node-level and graph-level downstream tasks have demonstrated that by combining a few simple but classical tasks, WAS can achieve comparable performance to other leading counterparts. The code is available at https://github.com/TianyuFan0504/WAS.